Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5723 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.2904. Min Act: -0.0000

Data Index: 446764 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.2274. Min Act: -0.0000

Data Index: 374011 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.2253. Min Act: -0.0000

Data Index: 857198 (C4 (Web Text))

Max Activating Token Index: 702

Text #3

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.2282. Min Act: -0.0000

Data Index: 688268 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.2182. Min Act: -0.0000

Data Index: 410686 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.2193. Min Act: -0.0000

Data Index: 465148 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.2130. Min Act: -0.0000

Data Index: 553603 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.2095. Min Act: -0.0000

Data Index: 771850 (C4 (Web Text))

Max Activating Token Index: 953

Text #8

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.1930. Min Act: -0.0000

Data Index: 1228499 (C4 (Web Text))

Max Activating Token Index: 687

Text #9

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.2002. Min Act: -0.0000

Data Index: 1013817 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.2074. Min Act: -0.0000

Data Index: 1127988 (C4 (Web Text))

Max Activating Token Index: 585

Text #11

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.2029. Min Act: -0.0000

Data Index: 391276 (C4 (Web Text))

Max Activating Token Index: 303

Text #12

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.1962. Min Act: -0.0000

Data Index: 238957 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.1998. Min Act: -0.0000

Data Index: 1291383 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.2065. Min Act: -0.0000

Data Index: 34416 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.1983. Min Act: -0.0000

Data Index: 960085 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.2050. Min Act: -0.0000

Data Index: 99937 (C4 (Web Text))

Max Activating Token Index: 315

Text #17

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.1978. Min Act: -0.0000

Data Index: 820428 (C4 (Web Text))

Max Activating Token Index: 84

Text #18

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.2047. Min Act: -0.0000

Data Index: 266435 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.1893. Min Act: -0.0000

Data Index: 768803 (C4 (Web Text))

Max Activating Token Index: 75